[Enhance] Support CPU Training (#1196)

* add cpu support

* fix

* fix comments

docs/en/1_exist_data_model.md

@@ -9,6 +9,7 @@ For high-level apis easier to integrated into other projects and basic demos, pl
 ### Test existing models on standard datasets
 
 - single GPU
+- CPU
 - single node multiple GPU
 - multiple node
 
@@ -18,10 +19,18 @@ You can use the following commands to test a dataset.
 # single-gpu testing
 python tools/test.py ${CONFIG_FILE} ${CHECKPOINT_FILE} [--out ${RESULT_FILE}] [--eval ${EVAL_METRICS}] [--show] [--show-dir ${SHOW_DIR}]
 
+# CPU: disable GPUs and run single-gpu testing script (experimental)
+export CUDA_VISIBLE_DEVICES=-1
+python tools/test.py ${CONFIG_FILE} ${CHECKPOINT_FILE} [--out ${RESULT_FILE}] [--eval ${EVAL_METRICS}] [--show] [--show-dir ${SHOW_DIR}]
+
 # multi-gpu testing
 ./tools/dist_test.sh ${CONFIG_FILE} ${CHECKPOINT_FILE} ${GPU_NUM} [--out ${RESULT_FILE}] [--eval ${EVAL_METRICS}]
 ```
 
+**Note**:
+
+For now, CPU testing is only supported for SMOKE.
+
 Optional arguments:
 - `RESULT_FILE`: Filename of the output results in pickle format. If not specified, the results will not be saved to a file.
 - `EVAL_METRICS`: Items to be evaluated on the results. Allowed values depend on the dataset. Typically we default to use official metrics for evaluation on different datasets, so it can be simply set to `mAP` as a placeholder for detection tasks, which applies to nuScenes, Lyft, ScanNet and SUNRGBD. For KITTI, if we only want to evaluate the 2D detection performance, we can simply set the metric to `img_bbox` (unstable, stay tuned). For Waymo, we provide both KITTI-style evaluation (unstable) and Waymo-style official protocol, corresponding to metric `kitti` and `waymo` respectively. We recommend to use the default official metric for stable performance and fair comparison with other methods. Similarly, the metric can be set to `mIoU` for segmentation tasks, which applies to S3DIS and ScanNet.
@@ -145,6 +154,20 @@ python tools/train.py ${CONFIG_FILE} [optional arguments]
 
 If you want to specify the working directory in the command, you can add an argument `--work-dir ${YOUR_WORK_DIR}`.
 
+### Training with CPU (experimental)
+
+The process of training on the CPU is consistent with single GPU training. We just need to disable GPUs before the training process.
+
+```shell
+export CUDA_VISIBLE_DEVICES=-1
+```
+
+And then run the script of train with a single GPU.
+
+**Note**:
+
+For now, most of the point cloud related algorithms rely on 3D CUDA op, which can not be trained on CPU. Some monocular 3D object detection algorithms, like FCOS3D and SMOKE can be trained on CPU. We do not recommend users to use CPU for training because it is too slow. We support this feature to allow users to debug certain models on machines without GPU for convenience.
+
 ### Train with multiple GPUs
 
 ```shell

docs/zh_cn/1_exist_data_model.md

@@ -18,10 +18,18 @@
 # 单块显卡测试
 python tools/test.py ${CONFIG_FILE} ${CHECKPOINT_FILE} [--out ${RESULT_FILE}] [--eval ${EVAL_METRICS}] [--show] [--show-dir ${SHOW_DIR}]
 
+# CPU：禁用显卡并运行单块 CPU 测试脚本（实验性）
+export CUDA_VISIBLE_DEVICES=-1
+python tools/test.py ${CONFIG_FILE} ${CHECKPOINT_FILE} [--out ${RESULT_FILE}] [--eval ${EVAL_METRICS}] [--show] [--show-dir ${SHOW_DIR}]
+
 # 多块显卡测试
 ./tools/dist_test.sh ${CONFIG_FILE} ${CHECKPOINT_FILE} ${GPU_NUM} [--out ${RESULT_FILE}] [--eval ${EVAL_METRICS}]
 ```
 
+**注意**:
+
+目前我们只支持 SMOKE 的 CPU 推理测试。
+
 可选参数：
 - `RESULT_FILE`：输出结果（pickle 格式）的文件名，如果未指定，结果不会被保存。
 - `EVAL_METRICS`：在结果上评测的项，不同的数据集有不同的合法值。具体来说，我们默认对不同的数据集都使用各自的官方度量方法进行评测，所以对 nuScenes、Lyft、ScanNet 和 SUNRGBD 这些数据集来说在检测任务上可以简单设置为 `mAP`；对 KITTI 数据集来说，如果我们只想评测 2D 检测效果，可以将度量方法设置为 `img_bbox`；对于 Waymo 数据集，我们提供了 KITTI 风格（不稳定）和 Waymo 官方风格这两种评测方法，分别对应 `kitti` 和 `waymo`，我们推荐使用默认的官方度量方法，它的性能稳定而且可以与其它算法公平比较；同样地，对 S3DIS、ScanNet 这些数据集来说，在分割任务上的度量方法可以设置为 `mIoU`。
@@ -143,6 +151,20 @@ python tools/train.py ${CONFIG_FILE} [optional arguments]
 
 如果你想在命令中指定工作目录，添加参数 `--work-dir ${YOUR_WORK_DIR}`。
 
+### 使用 CPU 进行训练 (实验性)
+
+在 CPU 上训练的过程与单 GPU 训练一致。 我们只需要在训练过程之前禁用显卡。
+
+```shell
+export CUDA_VISIBLE_DEVICES=-1
+```
+
+之后运行单显卡训练脚本即可。
+
+**注意**：
+
+目前，大多数点云相关算法都依赖于 3D CUDA 算子，无法在 CPU 上进行训练。 一些单目 3D 物体检测算法，例如 FCOS3D、SMOKE 可以在 CPU 上进行训练。我们不推荐用户使用 CPU 进行训练，这太过缓慢。我们支持这个功能是为了方便用户在没有显卡的机器上调试某些特定的方法。
+
 ### 使用多块显卡进行训练
 
 ```shell